© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94933
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traditionnel
    -0.61
     énergé
    -0.61
     traditionnels
    -0.60
    ">//
    -0.60
     tää
    -0.59
     traditionnelle
    -0.58
     Chwiliwch
    -0.57
    MessageTagHelper
    -0.57
     sonno
    -0.57
     clás
    -0.56
    POSITIVE LOGITS
     later
    0.71
     poi
    0.65
     then
    0.56
    BeforeEach
    0.56
     subsequently
    0.54
     thereafter
    0.54
     eventually
    0.53
     позже
    0.52
     subsequent
    0.52
     später
    0.51
    Activations Density 0.001%

    No Known Activations